CodeSOTAβOriginal site ↗
← Natural language inference

Completed / CodeSOTA execution on White

Inspect the measurement.

Qwen/Qwen2.5-0.5B · SNLI · 37.5% accuracy

32-example pilot. Pilot subset, CodeSOTA batched-v2 execution. Separate scope from serial v1; unchanged prompt/tokenization/metric contracts.
Run ID / completed
2933b280610cb03f5f2345c2
17 Oct 2026, 00:47 UTC
Model revision
060db6499f32faf8b98477b0a26969ef7d8b9987
Comparison scope
3ef5086324e4a200ffa81c1058aab801250aedfad5e4f11c7c4b8a63c1bf5b3e
Evaluator SHA-256
bc899fb160f6881408863cd8bcdf96102dd6d8b10559a5f781a8cd816103da77
Observed resources
1s elapsed · 0.96 GiB peak torch allocation
Dollar cost: not measured

Download evidence

Example-level outputs

All 32 scored examples. Ground truth and model predictions are preserved in the downloadable JSONL.

{"choices":["entailment","neutral","contradiction"],"id":"0","log_likelihood_mean":[-6.182082653045654,-14.555327415466309,-7.117827415466309],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"1","log_likelihood_mean":[-5.93580436706543,-15.493745803833008,-10.32449722290039],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"2","log_likelihood_mean":[-5.276850700378418,-10.832584381103516,-7.684146881103516],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"3","log_likelihood_mean":[-4.206663131713867,-10.395508766174316,-9.727540016174316],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"4","log_likelihood_mean":[-3.35693097114563,-10.446054458618164,-9.457773208618164],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"5","log_likelihood_mean":[-3.762688398361206,-10.765849113464355,-8.992411613464355],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"6","log_likelihood_mean":[-4.24653959274292,-8.354655265808105,-9.960124015808105],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"7","log_likelihood_mean":[-3.4588403701782227,-8.412422180175781,-9.939765930175781],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"8","log_likelihood_mean":[-3.5959975719451904,-8.577300071716309,-9.327300071716309],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"9","log_likelihood_mean":[-3.6602327823638916,-9.208524703979492,-7.009305953979492],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"10","log_likelihood_mean":[-3.141021251678467,-10.34283447265625,-8.22955322265625],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"11","log_likelihood_mean":[-3.1177966594696045,-10.158421516418457,-7.615452289581299],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"12","log_likelihood_mean":[-2.776639699935913,-8.560985565185547,-8.260204315185547],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"13","log_likelihood_mean":[-3.60390043258667,-8.951944351196289,-8.795694351196289],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"14","log_likelihood_mean":[-3.264570713043213,-7.520341873168945,-5.850255489349365],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"15","log_likelihood_mean":[-3.7721149921417236,-8.867087364196777,-4.835119247436523],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"16","log_likelihood_mean":[-4.216691970825195,-11.231144905090332,-9.031926155090332],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"17","log_likelihood_mean":[-4.008910179138184,-11.364415168762207,-7.063633918762207],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"18","log_likelihood_mean":[-3.5465269088745117,-11.06208610534668,-11.72419548034668],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"19","log_likelihood_mean":[-4.1725945472717285,-9.456588745117188,-10.862838745117188],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"20","log_likelihood_mean":[-2.479235887527466,-10.461469650268555,-10.258344650268555],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"21","log_likelihood_mean":[-3.0550248622894287,-9.032089233398438,-10.625839233398438],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"22","log_likelihood_mean":[-3.2678475379943848,-9.913921356201172,-13.392436981201172],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"23","log_likelihood_mean":[-3.7637088298797607,-10.616063117980957,-11.307469367980957],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"24","log_likelihood_mean":[-3.301624059677124,-11.38060188293457,-10.03685188293457],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"25","log_likelihood_mean":[-4.03183126449585,-12.1359281539917,-9.4562406539917],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"26","log_likelihood_mean":[-2.939894199371338,-11.68382453918457,-9.38109016418457],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"27","log_likelihood_mean":[-2.8297297954559326,-8.794330596923828,-9.763080596923828],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"28","log_likelihood_mean":[-3.4475297927856445,-8.762885093688965,-10.551947593688965],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"29","log_likelihood_mean":[-4.248393535614014,-8.727792739868164,-7.719980239868164],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"30","log_likelihood_mean":[-3.9375245571136475,-6.610547065734863,-8.149609565734863],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"31","log_likelihood_mean":[-3.845025062561035,-7.11165189743042,-9.322589874267578],"prediction":0,"reference":0,"score":1.0}